Video
MiniMax H3 Max
H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality
- Text to video
- Image to video
- Video editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for MiniMax H3 Max. Review your own result before publishing.
Use MiniMax H3 Max through the API.
Start with this model ID for the endpoint featured on this page:
minimax/h3-max/text-to-video
Available modes
- text-to-video ·
minimax/h3-max/text-to-video - image-to-video (h3-max/image-to-video) ·
minimax/h3-max/image-to-video - image-to-video (camera-controls) ·
minimax/h3-max/camera-controls - image-to-video (reference-to-video) ·
minimax/h3-max/reference-to-video - image-to-video (lip-sync/image-to-video) ·
minimax/h3-max/lip-sync/image-to-video - video-to-video (insert-video) ·
minimax/h3-max/insert-video - video-to-video (extend-video) ·
minimax/h3-max/extend-video - video-to-video (3d-to-video) ·
minimax/h3-max/3d-to-video
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.